--- license: apache-2.0 tags: - generated_from_trainer model-index: - name: ai-light-dance_singing3_ft_wav2vec2-large-xlsr-53-v1-5gram results: [] --- # ai-light-dance_singing3_ft_wav2vec2-large-xlsr-53-v1-5gram This model is a fine-tuned version of [gary109/ai-light-dance_singing3_ft_wav2vec2-large-xlsr-53-v1-5gram](https://huggingface.co/gary109/ai-light-dance_singing3_ft_wav2vec2-large-xlsr-53-v1-5gram) on the None dataset. It achieves the following results on the evaluation set: - Loss: 0.5111 - Wer: 0.1961 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 4e-06 - train_batch_size: 4 - eval_batch_size: 4 - seed: 42 - gradient_accumulation_steps: 4 - total_train_batch_size: 16 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_steps: 500 - num_epochs: 100.0 - mixed_precision_training: Native AMP ### Training results | Training Loss | Epoch | Step | Validation Loss | Wer | |:-------------:|:-----:|:-----:|:---------------:|:------:| | 0.3028 | 1.0 | 288 | 0.4693 | 0.2046 | | 0.2986 | 2.0 | 576 | 0.4828 | 0.2058 | | 0.297 | 3.0 | 864 | 0.5020 | 0.2038 | | 0.2863 | 4.0 | 1152 | 0.5216 | 0.2020 | | 0.3036 | 5.0 | 1440 | 0.4963 | 0.2008 | | 0.3141 | 6.0 | 1728 | 0.5005 | 0.2020 | | 0.2898 | 7.0 | 2016 | 0.4962 | 0.2029 | | 0.2922 | 8.0 | 2304 | 0.5073 | 0.2031 | | 0.266 | 9.0 | 2592 | 0.5159 | 0.2024 | | 0.2817 | 10.0 | 2880 | 0.5238 | 0.2011 | | 0.2922 | 11.0 | 3168 | 0.5080 | 0.2011 | | 0.2869 | 12.0 | 3456 | 0.4974 | 0.2027 | | 0.284 | 13.0 | 3744 | 0.5104 | 0.2006 | | 0.2911 | 14.0 | 4032 | 0.5026 | 0.2017 | | 0.2864 | 15.0 | 4320 | 0.5065 | 0.2002 | | 0.2779 | 16.0 | 4608 | 0.5024 | 0.2010 | | 0.2766 | 17.0 | 4896 | 0.5078 | 0.1998 | | 0.2872 | 18.0 | 5184 | 0.5114 | 0.1981 | | 0.268 | 19.0 | 5472 | 0.5078 | 0.1980 | | 0.2631 | 20.0 | 5760 | 0.5262 | 0.2021 | | 0.2753 | 21.0 | 6048 | 0.5161 | 0.1991 | | 0.2797 | 22.0 | 6336 | 0.5097 | 0.2009 | | 0.2667 | 23.0 | 6624 | 0.5131 | 0.1995 | | 0.2722 | 24.0 | 6912 | 0.5098 | 0.1990 | | 0.3026 | 25.0 | 7200 | 0.5193 | 0.2006 | | 0.2888 | 26.0 | 7488 | 0.4987 | 0.1986 | | 0.2732 | 27.0 | 7776 | 0.5063 | 0.2007 | | 0.2567 | 28.0 | 8064 | 0.5103 | 0.2015 | | 0.2845 | 29.0 | 8352 | 0.5084 | 0.2020 | | 0.2591 | 30.0 | 8640 | 0.5109 | 0.1989 | | 0.2777 | 31.0 | 8928 | 0.5179 | 0.1994 | | 0.2784 | 32.0 | 9216 | 0.5183 | 0.1989 | | 0.2801 | 33.0 | 9504 | 0.5222 | 0.2003 | | 0.2554 | 34.0 | 9792 | 0.5137 | 0.1990 | | 0.2708 | 35.0 | 10080 | 0.5094 | 0.1964 | | 0.27 | 36.0 | 10368 | 0.5076 | 0.1980 | | 0.2706 | 37.0 | 10656 | 0.5179 | 0.1983 | | 0.2791 | 38.0 | 10944 | 0.5154 | 0.1976 | | 0.3148 | 39.0 | 11232 | 0.5082 | 0.1990 | | 0.2834 | 40.0 | 11520 | 0.5107 | 0.1980 | | 0.2739 | 41.0 | 11808 | 0.5009 | 0.1990 | | 0.2687 | 42.0 | 12096 | 0.5232 | 0.2011 | | 0.2696 | 43.0 | 12384 | 0.5108 | 0.1986 | | 0.2729 | 44.0 | 12672 | 0.5159 | 0.1991 | | 0.2579 | 45.0 | 12960 | 0.5162 | 0.1991 | | 0.283 | 46.0 | 13248 | 0.5032 | 0.1982 | | 0.282 | 47.0 | 13536 | 0.5107 | 0.1980 | | 0.2708 | 48.0 | 13824 | 0.5128 | 0.1982 | | 0.2562 | 49.0 | 14112 | 0.5163 | 0.1991 | | 0.2675 | 50.0 | 14400 | 0.5062 | 0.1994 | | 0.285 | 51.0 | 14688 | 0.4999 | 0.1988 | | 0.2756 | 52.0 | 14976 | 0.5030 | 0.1986 | | 0.2888 | 53.0 | 15264 | 0.5043 | 0.1975 | | 0.2778 | 54.0 | 15552 | 0.5111 | 0.1980 | | 0.2707 | 55.0 | 15840 | 0.5117 | 0.1995 | | 0.2566 | 56.0 | 16128 | 0.5197 | 0.2002 | | 0.2517 | 57.0 | 16416 | 0.5211 | 0.1977 | | 0.2629 | 58.0 | 16704 | 0.5080 | 0.1986 | | 0.2787 | 59.0 | 16992 | 0.5133 | 0.1980 | | 0.269 | 60.0 | 17280 | 0.5156 | 0.1973 | | 0.2664 | 61.0 | 17568 | 0.5192 | 0.1949 | | 0.2605 | 62.0 | 17856 | 0.5095 | 0.1970 | | 0.2649 | 63.0 | 18144 | 0.5149 | 0.1970 | | 0.246 | 64.0 | 18432 | 0.5165 | 0.1975 | | 0.2567 | 65.0 | 18720 | 0.5072 | 0.1981 | | 0.2509 | 66.0 | 19008 | 0.5061 | 0.1978 | | 0.289 | 67.0 | 19296 | 0.5087 | 0.1957 | | 0.2511 | 68.0 | 19584 | 0.5168 | 0.1982 | | 0.2623 | 69.0 | 19872 | 0.5110 | 0.1959 | | 0.2762 | 70.0 | 20160 | 0.5123 | 0.1959 | | 0.2704 | 71.0 | 20448 | 0.5118 | 0.1966 | | 0.2854 | 72.0 | 20736 | 0.5128 | 0.1949 | | 0.2602 | 73.0 | 21024 | 0.5094 | 0.1966 | | 0.2675 | 74.0 | 21312 | 0.5058 | 0.1961 | | 0.2519 | 75.0 | 21600 | 0.5216 | 0.1988 | | 0.2666 | 76.0 | 21888 | 0.5117 | 0.1959 | | 0.2637 | 77.0 | 22176 | 0.5058 | 0.1957 | | 0.273 | 78.0 | 22464 | 0.5187 | 0.1966 | | 0.2666 | 79.0 | 22752 | 0.5176 | 0.1958 | | 0.2627 | 80.0 | 23040 | 0.5142 | 0.1950 | | 0.2508 | 81.0 | 23328 | 0.5158 | 0.1961 | | 0.2499 | 82.0 | 23616 | 0.5131 | 0.1970 | | 0.2583 | 83.0 | 23904 | 0.5150 | 0.1975 | | 0.246 | 84.0 | 24192 | 0.5097 | 0.1962 | | 0.272 | 85.0 | 24480 | 0.5043 | 0.1950 | | 0.2601 | 86.0 | 24768 | 0.5091 | 0.1961 | | 0.2719 | 87.0 | 25056 | 0.5087 | 0.1975 | | 0.269 | 88.0 | 25344 | 0.5126 | 0.1966 | | 0.2863 | 89.0 | 25632 | 0.5174 | 0.1966 | | 0.2581 | 90.0 | 25920 | 0.5159 | 0.1969 | | 0.26 | 91.0 | 26208 | 0.5146 | 0.1969 | | 0.2796 | 92.0 | 26496 | 0.5150 | 0.1966 | | 0.2723 | 93.0 | 26784 | 0.5133 | 0.1971 | | 0.249 | 94.0 | 27072 | 0.5096 | 0.1961 | | 0.266 | 95.0 | 27360 | 0.5116 | 0.1964 | | 0.2683 | 96.0 | 27648 | 0.5133 | 0.1967 | | 0.2451 | 97.0 | 27936 | 0.5141 | 0.1965 | | 0.2723 | 98.0 | 28224 | 0.5123 | 0.1962 | | 0.2527 | 99.0 | 28512 | 0.5120 | 0.1966 | | 0.2604 | 100.0 | 28800 | 0.5111 | 0.1961 | ### Framework versions - Transformers 4.21.0.dev0 - Pytorch 1.9.1+cu102 - Datasets 2.3.3.dev0 - Tokenizers 0.12.1